David Ondrej's Agent Skills is a repository of reusable instruction packages for AI coding, research, and workflow agents. Each skill describes a focused process for tasks such as code improvement, research, documentation, transcript work, and agent coordination. The catalogue entries are the repository's own skills and related agent configuration.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add davidondrej/skills --skill pi-web-searchgit clone --depth 1 https://github.com/davidondrej/skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/davidondrej/skills/pi-web-search)<a href="https://agentmods.dev/skills/davidondrej/skills/pi-web-search"><img src="https://agentmods.dev/badge/skills/davidondrej/skills/pi-web-search/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/davidondrej/skills/pi-web-search"><img src="https://agentmods.dev/badge/skills/davidondrej/skills/pi-web-search.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Data Exfiltration · line 49 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00066 | $0.00816 |
| Opus 5 | $0.00033 | $0.00408 |
| Sonnet 5 | $0.00013 | $0.00163 |
| Haiku 4.5 | $0.00007 | $0.00082 |
Grade A, and why
pi-web-search scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s --max-time 60 "https://deepapi.co/v1/search/web" \ Copies of this mod
1 near-identical copy found in the catalogue:
- pi-web-search — 92% identical, 10 lines differ
How it starts
The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web Search
The pi-web-access package is installed globally. Zero-config via Exa MCP (no API key), with fallback Exa → Perplexity → Gemini.
CRITICAL: always pass workflow: "none"
Every web_search call MUST include workflow: "none". This skips the interactive browser curator popup (the user does not want it opening). No exceptions — single query or batched queries, always set workflow: "none".
web_search({ queries: ["query 1", "query 2"], workflow: "none" })
Tools
web_search— search the web; returns synthesized answers with citations. Can be called many times per turn. Always passworkflow: "none".code_search— zero-key Exa code-context. Use for library/API/code lookups instead of genericweb_search.fetch_content— fetch URL(s) → markdown; handles PDFs, YouTube, GitHub.get_search_content— big pages (>30k chars) are truncated in responses but stored in full; call this to pull the rest on demand so they don't blow context.
fetch_content specifics
- GitHub URLs are cloned, not scraped — you get real files + a local path to explore with
read/bash(private repos need theghCLI). Use this for dev work. - PDFs → auto-extracted to markdown in
~/Downloads/, readable in sections (text-only, no OCR). - YouTube/video → full raw transcripts + frame extraction. Needs a
GEMINI_API_KEY(not zero-config); frame extraction also needsffmpeg/yt-dlp.
Routing — match the user's phrasing
Always use the web_search tool. These counts are HARD MINIMUMS — count your queries before answering and do not stop short:
- "web search" → at least 2 queries, varied keywords/angles, then synthesize.
- "extensive web research" → at least 4 queries, totally different keywords and angles.
- "deep research" → at least 8 queries, totally different keywords and angles, run across 2–3 successive batches (refine angles after each batch), to learn as much as possible about the topic.
A single batched web_search call counts each query in queries[] toward the total. If your first batch is under the minimum, fire another batch before synthesizing.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 7d ago Changed 7207e2576ce2
- 12d ago First seen · 56 lines · 66 tokens per session scan A c6b328116925
pi-web-search is a skill published in the GitHub repository davidondrej/skills (4,012 stars, last pushed yesterday), licensed MIT. It adds 66 tokens to every session and 816 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…